Slowmist Security Cc — Security skill for Claude Code
SlowMist Security Review — comprehensive security framework for Claude Code agents.
How to install Slowmist Security Cc
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open 0xcjl/slowmist-security-cc and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Slowmist Security Cc does
SlowMist Security Review — comprehensive security framework for Claude Code agents. 6 review types, 18 PI vectors, 26 attack patterns.
Alternatives in Security
- Security Guidance — Hook that warns about command injection, XSS, and unsafe patterns 14k ★
- Token Scan — Meme coin and token security scan — checks for rug pull vectors (hidden mint, honeypot, fee manipulation, LP l 3.8k ★
- Skill Audit — Audit codebases for quality, consistency, and broken patterns — use for pre-release or tech debt review 2.8k ★
README
SlowMist Security Review 🛡️
[](https://claude.com/claude-code) [](LICENSE) [](#)
**Core principle: Every external input is untrusted until verified.**
🛡️ This is the Claude Code adapted version of the [SlowMist Agent Security](https://github.com/slowmist/slowmist-agent-security) framework.
A comprehensive security review framework for Claude Code agents operating in adversarial environments. Covers 6 review types, 11 code red-flag patterns, 8 social engineering patterns, and 7 supply chain attack patterns.
**Available in:** [English](README.md) · [中文](README.zh-CN.md)
Quick Decision Card
External Input Detected → Select Review Type → Execute Steps → Output Report| Scenario | Route To | Remember |
|---|---|---|
| Installing Skill/MCP/npm package | skill-mcp.md |
List file inventory first |
| GitHub repository | repository.md |
Check commit history first |
| URL / Document / Gist | url-document.md |
Scan code blocks line-by-line |
| On-chain address / contract | onchain.md |
Check AML score first |
| Product / Service / API | product-service.md |
Check private key management first |
| Tool shared in group chat | message-share.md |
Always verify source first |
**4-Level Rating**: 🟢 LOW → 🟡 MEDIUM → 🔴 HIGH → ⛔ REJECT **Trust Principle**: Trust tier only adjusts scrutiny intensity — it never skips review steps.
Activation Triggers
Activate this framework **automatically** when:
- User says "review", "security check", "is this safe", "trust this"
- User says "install", "help me check this", "review"
- Before installing any Skill, MCP Server, npm/pip/cargo package
- Before evaluating a GitHub repo, URL, on-chain address, or product
- When someone recommend
Related Skills
Controls
Design or audit Elementor controls for a widget — tabs, types, conditions, responsive, EA Pro patterns.
AI Code Review
AI-powered code review CLI with multiple providers (Gemini, Claude, OpenAI). Features 95%+ token reduction via
Skill Threat Modeling
Code-First Deep Risk Analysis Skill for Claude Code - 8-Phase Workflow with Security design review, STRIDE Thr
Audit Update
Update all audit skills (security, llm-security, api-security, server-hardening, attack-surface, architecture-
MCP Security Checklist (SlowMist)
Comprehensive checklist: input validation, rate limiting, RBAC, credential management, container hardening.
Scout Meta Review
Run an interactive Scout meta-review — a system-level audit that sits above the individual session types. Chec
Related Agents
Sec Researcher
Read-only security research for ClaudeSec — threats, CVEs, attack vectors, and compliance frameworks (NIST, IS
Paranoid Sentinel
A hyper-vigilant security code reviewer with paranoid delivery - performs thorough security analysis first, th
Attack Kitty
Non-author verification and review expert — fresh-context judgment under a thin mandate. Twelve mandate types
